ConvLab-3
ConvLab-3 copied to clipboard
ConvLab
**Describe the feature** Transform the following datasets into the [Unified format](https://github.com/ConvLab/ConvLab-3/blob/master/data/unified_datasets/README.md) under `data/unified_datasets`. Suggestions of adding/deleting datasets are welcome! - [x] MultiWOZ 2.1 - [ ] MultiWOZ 2.2 - [...
- **Name:** GlobalWoz - **Description:** a large-scale multilingual ToD dataset globalized from an English ToD dataset for three unexplored use cases of multilingual ToD systems. - **Paper:** https://aclanthology.org/2022.acl-long.115.pdf - **Data:**...
Could you kindly provide an example to demonstrate how to utilize this project to build a task-oriented dialogue system based on Large Language Models (LLMs)?
**Description:** ### python train_ppo.py --config_name="llamaSimulator"，There is no progress bar when using, whether it is training or not (ETOD) PS D:\Prompting-LLMs-for-User-Simulation-in-TOD\convlab\policy\ppo> python train_ppo.py --config_name="llamaSimulator" Visible device: cuda Vectorizer: Data set used...
It came to my attention that in the KVRET dataset ([permalink](https://github.com/ConvLab/ConvLab-3/blob/d24454a7b4018a0be18c2e4550fb826980064530/data/unified_datasets/kvret/data.zip)), the file `dialogues.json` has one sample that contains overlapping slots: ```json { "speaker": "user", "utterance": "I need the reminder...
**Describe the bug** Cloning fails in the lfs stage **To Reproduce** Steps to reproduce the behavior: ```bash cd /tmp git clone --depth 1 https://github.com/ConvLab/ConvLab-3.git ``` Results in this: ``` Cloning...
